diff options
| author | Patrick Simianer <p@simianer.de> | 2013-11-13 18:12:10 +0100 |
|---|---|---|
| committer | Patrick Simianer <p@simianer.de> | 2013-11-13 18:12:10 +0100 |
| commit | d6e6babf2cfe49fed040b651624b7e34d1a9b507 (patch) | |
| tree | 2a00ab18f10a7f93e7e172551c01b48cc9f20b8c /corpus | |
| parent | 2d2d5eced93d58bc77894d8c328195cd9950b96d (diff) | |
| parent | 8a24bb77bc2e9fd17a6f6529a2942cde96a6af49 (diff) | |
merge w/ upstream
Diffstat (limited to 'corpus')
| -rwxr-xr-x | corpus/tokenize-anything.sh | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/corpus/tokenize-anything.sh b/corpus/tokenize-anything.sh index a20a022f..c7adfa61 100755 --- a/corpus/tokenize-anything.sh +++ b/corpus/tokenize-anything.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/usr/bin/env bash ROOTDIR=`dirname $0` SUPPORT=$ROOTDIR/support @@ -12,8 +12,8 @@ fi $SUPPORT/utf8-normalize.sh $NORMARGS | $SUPPORT/quote-norm.pl | $SUPPORT/tokenizer.pl | - sed -u -e 's/ al - / al-/g' | + sed -e 's/ al - / al-/g' | $SUPPORT/fix-contract.pl | - sed -u -e 's/^ //' | sed -u -e 's/ $//' | + sed -e 's/^ //' | sed -e 's/ $//' | perl -e '$|++; while(<>){s/(\d+)(\.+)$/$1 ./; s/(\d+)(\.+) \|\|\|/$1 . |||/; print;}' |